Improving Drug–Drug Interaction Extraction with Gaussian Noise

Drug–Drug Interactions (DDIs) produce essential and valuable insights for healthcare professionals, since they provide data on the impact of concurrent administration medications to patients during therapy. In that sense, some relevant works, related DDIExtraction2013 Challenge, are available in current technical literature. This study aims improve previous results, using two models, where a Gaussian noise layer is added achieve better DDI relationship extraction. (1) A Piecewise Convolutional Neural Network (PW-CNN) model used capture relationships among pharmacological entities described biomedical databases. Additionally, incorporates multichannel words enrich person’s vocabulary reduce unfamiliar words. (2) The uses pre-trained BERT language classify relationships, while also integrating from target entities. After identifying entities, transfers information through architecture integrates encoded both results experiment show an improved performance, with respect models.